© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 119480
    Prev
    Next
    INDEX
    Explanations

    themes related to growth and change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ico
    -0.06
    imo
    -0.06
    Ãłng
    -0.06
    ilateral
    -0.06
    íģ
    -0.06
    ãģ¦
    -0.06
    ilter
    -0.06
    odzi
    -0.06
    enville
    -0.06
     bana
    -0.06
    POSITIVE LOGITS
    äºĨä¸Ģ
    0.08
    irá
    0.07
    avr
    0.07
    OLUM
    0.07
     annually
    0.07
     äºĨ
    0.07
     tomorrow
    0.07
    daily
    0.07
     hereby
    0.07
    BH
    0.07
    Activations Density 0.236%

    No Known Activations